Guangdong Provincial Key Laboratory of Intelligent Transportation System

Guangzhou, China

Guangdong Provincial Key Laboratory of Intelligent Transportation System

Guangzhou, China

Time filter

Source Type

Wang H.,Sun Yat Sen University | Wang H.,Guangdong Provincial Key Laboratory of Intelligent Transportation System | Wang H.,Center for Monitoring Research | Cai M.,Sun Yat Sen University | And 5 more authors.
Journal of Environmental Management | Year: 2017

The primary objective of this study is the development and application of a 3D road traffic noise attenuation calculation algorithm. First, the traditional empirical method does not address problems caused by non-direct occlusion by buildings and the different building heights. In contrast, this study considers the volume ratio of the buildings and the area ratio of the projection of buildings adjacent to the road. The influence of the ground affection is analyzed. The insertion loss due to barriers (infinite length and finite barriers) is also synthesized in the algorithm. Second, the impact of different road segmentation is analyzed. Through the case of Pearl River New Town, it is recommended that 5° is the most appropriate scanning angle as the computational time is acceptable and the average error is approximately 3.1 dB. In addition, the algorithm requires only 1/17 of the time that the beam tracking method requires at the cost of more imprecise calculation results. Finally, the noise calculation for a large urban area with a high density of buildings shows the feasibility of the 3D noise attenuation calculation algorithm. The algorithm is expected to be applied in projects requiring large area noise simulations. © 2017 Elsevier Ltd


Wei Q.-B.,Data Management | He Z.-C.,Sun Yat Sen University | He Z.-C.,Guangdong Provincial Key Laboratory of Intelligent Transportation System | Zheng X.-S.,Guangzhou Transport Information & Control Center | And 2 more authors.
Jiaotong Yunshu Xitong Gongcheng Yu Xinxi/Journal of Transportation Systems Engineering and Information Technology | Year: 2017

Based on studying the change rules of macroscopic urban traffic, and comprehensive consideration the factors on the impact of traffic, such as: weather, holidays, major activities other factors, this paper establishes a K-Nearest Neighbor traffic performance index prediction model for the next 3 hours and 24 hours (every 5 minutes). Taking the effect of all the related factors into account, the model designs the state vectors, distance calculation and the prediction calculation method, calibrates parameters of the model with historical data, and then the traffic performance index of mid-term and short-term can be predicted. The test result with the traffic performance index of Guangzhou proves the proposed model has ideal prediction on both normal and special days with strong practicability and maneuverability. Copyright © 2017 by Science Press.


Niu Z.,Guangdong Provincial Key Laboratory of Intelligent Transportation System | Niu Z.,Sun Yat Sen University | Huang M.,Guangdong Provincial Key Laboratory of Intelligent Transportation System | Huang M.,Sun Yat Sen University | And 2 more authors.
Xitong Fangzhen Xuebao / Journal of System Simulation | Year: 2016

In order to realize the intelligent management of road guide signs, a method of visualization of road guide sign panel based on the flexible combination of guiding information was proposed. As a consequence of analysis for structures of guide sign panel, the message on the guide sign panel was decomposed into guiding information, and then visualization function was proposed. The panel style was determined by the physical and logical topology of guiding intersection dynamically with the help of guide sign system database. Then the composition of geography information and guiding information was utilized in the process of visualization. The visualization method was tested in the Guangzhou Higher Education Mega Center, and the visual panels created by the method shared the most widely features with guide panels in reality. The result reveals that the algorithm is feasible and effective. © 2016, The Editorial Board of Journal of System Simulation. All right reserved.


Li X.-Y.,Guangdong Provincial Key Laboratory of Intelligent Transportation System
2016 6th International Workshop on Computer Science and Engineering, WCSE 2016 | Year: 2016

Compressive Sensing is applicable to the sparse signals or sampling signals, and can compress the signal data properly in course of sampling, therefore, it can carry out sampling at a rate much lower than that specified as per Nyquist Sampling Theorem, and reconstruct the original signals accurately. This paper mainly studies the channel estimation algorithm of OFDM system, including the traditional channel estimation algorithm and that based on compressive sensing theory, and makes a relevant analysis on their respective theories, thoughts and characteristics. Furthermore, an experiment simulation is conducted here to compare their performance in an all-round manner, and the conclusion indicates that the signal acquisition technology based on compressive sensing technology performs better. The compressive sensing can effectively solve the problems encountered by the traditional signal sampling and coding technology in the aspect of processing speed, memory space and anti-interference function, showing a promising application background.


Li F.-W.,Sun Yat Sen University | Li F.-W.,Guangdong Provincial Key Laboratory of Intelligent Transportation System | Li F.-W.,Application Security | Li X.-Y.,Sun Yat Sen University | And 5 more authors.
Proceedings of SPIE - The International Society for Optical Engineering | Year: 2013

The radiator grille is an important feature to distinguish the style of vehicle, and also helpful to the automatic recognition of vehicle type. The radiator grille image which is split from the vehicle face is treated as a texture image. By analyzing the Fourier spectrum of the radiator grille image, visual features are extracted. According to the visual features, radiator grilles are classified into different sorts, such as longitudinal or transverse. Compared with other feature extraction methods, the test result shows that the proposed method is effective for the accuracy reaches more than 80%. © 2013 SPIE.


Qianyin J.,Sun Yat Sen University | Qianyin J.,Guangdong Provincial Key Laboratory of Intelligent Transportation System | Qianyin J.,Key Laboratory of Video and Image Intelligent Analysis and Application Technology of MPS | Guoming L.,Sun Yat Sen University | And 7 more authors.
2015 IEEE 1st International Smart Cities Conference, ISC2 2015 | Year: 2015

In order to reduce traffic accidents caused by the pedestrian, five kinds of dangerous pedestrian abnormal behaviors are studied in the paper. A behavior model between the pedestrian trajectory and the road is built to describe the five kinds of dangerous pedestrian abnormal behaviors: crossing road border, illegal stay, crossing the road, moving along the curb, entering road area. The method contains pedestrian detection, shadow elimination, pedestrian recognition, pedestrian tracking and abnormal behavior detection. Background subtraction method is used to detect moving targets. After shadow elimination, pedestrians are distinguished from vehicles according to the ratio. Then, pedestrian trajectories are gotten by pedestrian tracking. Finally, based on the relation between trajectory and road, the model of five kinds of pedestrian abnormal behaviors is established, and abnormal behaviors are detected according this model. Experiments show that the method can distinguish and detect the pedestrian abnormal behaviors effectively in short time, and it is suitable to use in real time traffic monitoring. © 2015 IEEE.


Xing H.,Sun Yat Sen University | Xing H.,Guangdong Provincial Key Laboratory of Intelligent Transportation System | Xu W.,Guangdong Provincial Key Laboratory of Intelligent Transportation System | Xu W.,Sun Yat Sen University | And 4 more authors.
Huanjing Kexue Xuebao/Acta Scientiae Circumstantiae | Year: 2011

Pollutant emissions in the street canyon with and without signals for pedestrians crossing were calculated by coupling traffic micro-simulation software with a vehicle emission model. With the simulation result as the emission source input, the flow and concentration field of the three-dimensional street canyon with the wind direction perpendicular to the street were modeled based on a k-ε model and the species transport equation. The result showed that the k-ε model and species transport equation can describe the pollutant dispersion in the three-dimensional street canyon well when the wind direction was perpendicular to the street. Two significant flow patterns can be discovered, corner eddies at the ends of the street canyon and a canyon vortex in the middle part of street canyon. The closer to the middle of street canyon, the angle between canyon vortex and the ground was nearer to 90°. The pollutant concentrations of windward and leeward side in the middle of the street canyon with signals for pedestrians crossing were 2.5 times and 2.7 times higher than the canyon without signals for pedestrians crossing. The pollutant concentration of the windward side was 18.88 mg·m-3, which was 0.89 times higher than the second National Standard.


Li L.,Sun Yat Sen University | Li L.,Guangdong Provincial Key Laboratory of Intelligent Transportation System | Li J.,Sun Yat Sen University | Li J.,Guangdong Provincial Key Laboratory of Intelligent Transportation System
Wuhan Ligong Daxue Xuebao/Journal of Wuhan University of Technology | Year: 2011

The generalized transit travel time is proposed in consideration of number of transfers, travel time, travel distance, walking distance, waiting time, etc; and the utility function of different transits are constructed according to the generalized transit travel time and travel cost. The nested-logit choice model is proposed to separate the modal choice and route choice. The case study of Guangzhou City is presented whose model parameters are obtained though questionnaire survey. A comparison between model results and survey data shows that the proposed model produces feasible and reliable results.


Hu J.-H.,Sun Yat Sen University | Hu J.-H.,Guangdong Provincial Key Laboratory of Intelligent Transportation System | Cheng Z.-F.,Sun Yat Sen University | Cheng Z.-F.,Guangdong Provincial Key Laboratory of Intelligent Transportation System | And 4 more authors.
Jiaotong Yunshu Xitong Gongcheng Yu Xinxi/Journal of Transportation Systems Engineering and Information Technology | Year: 2013

Bus isochrones indicate the maximum scale of bus system can extend during one time interval. A calculation method of isochrones is proposed in this paper and it can be applied to the analysis of public transport accessibility. The travel process by bus is analyzed and divided into five parts: walking to the bus stop from departure, waiting for buses, boarding buses, transfer and walking to the destination. Specific calculation methods of time cost are proposed for each part, respectively. Then, the isochrones are obtained by the grid method and the inverse distance weighting method. The bus GPS data of Guangzhou, China is used to draw the isochrones maps and to demonstrate the Tee mall. Furthermore, the space-time accessibility is measured in the covering area of a unit time isochrones and the accessibility differences of different directions are then analyzed through profiles. © 2011 by Science Press.


Hu J.-H.,Sun Yat Sen University | Hu J.-H.,Guangdong Provincial Key Laboratory of Intelligent Transportation System | Deng J.,Sun Yat Sen University | Deng J.,Guangdong Provincial Key Laboratory of Intelligent Transportation System | And 2 more authors.
Jiaotong Yunshu Xitong Gongcheng Yu Xinxi/Journal of Transportation Systems Engineering and Information Technology | Year: 2014

This paper summarizes the research status of identifying the alighting stations of smart card passengers for flat-rate fare lines. To make best use of passenger trip chains and passenger flow of stations, it analyzes transit travel characteristics and proposes a number of assumptions. Based on these assumptions, it defines relative variables to describe passenger trip chains and considers individual characteristics for alighting attraction weighting. Then, the paper combines disaggregate analysis and aggregate analysis according to the completeness of passenger trip chains and then formulates the bus passenger alighting weight model. It also proposes the algorithm to solve the established model and a calibration method of the model. Finally, it takes Line 448 in Guangzhou city as an example and compared the identifying results of this new model with the identifying results of the disaggregate analysis model. The results show that the new model is more applicative in identifying the alighting stations of smart card passengers and has high reliability in a cluster analysis.

Loading Guangdong Provincial Key Laboratory of Intelligent Transportation System collaborators
Loading Guangdong Provincial Key Laboratory of Intelligent Transportation System collaborators